Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) · 附件证据(ev-h55-card-healthbench)

Claude Haiku 5.5 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。证据 ev-h55-card-healthbench。

原文与定位

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / low配置,Length-adjusted score 59.9%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。 查看成绩条件

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / medium配置,Length-adjusted score 60.2%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。 查看成绩条件

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / high配置,Length-adjusted score 60.3%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。 查看成绩条件

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / xhigh配置,Length-adjusted score 61.1%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。 查看成绩条件

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / max配置,Length-adjusted score 61.6%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card》System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A。 查看成绩条件

HealthBench length-adjusted scores are labeled from 59.9% at low to 61.6% at max effort.
官方材料
Claude Haiku 5.5 System Card · PDF 第 134 页
定位
附件 · System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A
材料版本
144 页 PDF/TXT:本地留存副本、current-haiku-5-5-system-card.txt;封面日期 2026-10-07;正文 pp.1-144 已全文核读,全部63个含图/向量图表页实际视觉检查(本轮补看53页,合并此前10页),无未读页或未查看图表页;此为 current 卡片,不作为首发日附件证据。
版本公布
披露时间
未确认 · 首发/后补未确认
采集时间
历史依据
暂无可靠历史版本依据
引用文本

Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / low配置,Length-adjusted score 59.9%(具体成绩公布时间未确认);Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / medium配置,Length-adjusted score 60.2%(具体成绩公布时间未确认);Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / high配置,Length-adjusted score 60.3%(具体成绩公布时间未确认);Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / xhigh配置,Length-adjusted score 61.1%(具体成绩公布时间未确认);Claude Haiku 5.5 · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),Healthcare evaluations / max配置,Length-adjusted score 61.6%(具体成绩公布时间未确认)。官方出处 Claude Haiku 5.5 System Card(附件,144 页 PDF/TXT:本地留存副本、current-haiku-5-5-system-card.txt;封面日期 2026-10-07;正文 pp.1-144 已全文核读,全部63个含图/向量图表页实际视觉检查(本轮补看53页,合并此前10页),无未读页或未查看图表页;此为 current 卡片,不作为首发日附件证据。)System Card PDF pp.132-134, §§8.11.1, 8.11.3 and Figure 8.11.3.A,https://www.anthropic.com/claude-haiku-5-5-system-card#page=134。Benchlog https://benchlog.lekshome.cc/evidence/claude-haiku-5-5/ev-h55-card-healthbench/

关联成绩与条件

Claude Haiku 5.5 · HealthBench 成绩与配置
指标与成绩配置与评测条件证据关系
Length-adjusted score59.9%原文 59.9% · 单位 %
公布 未确认
Healthcare evaluations / low
设置
Safety classifiers enabled; low effort; run counts, scoring variants, and dates are recorded per result.
未知项
Healthcare evaluations use benchmark-specific run counts and scoring variants.
工具
禁止工具
推理预算
low
框架
未记录
协议
HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
条件
low effort; one run per level below max and five runs at max. Runs below max were made October 5; max is a five-run mean from October 2. Labeled figure value.

直接支持该成绩

在排名中查看此成绩
Length-adjusted score60.2%原文 60.2% · 单位 %
公布 未确认
Healthcare evaluations / medium
设置
Safety classifiers enabled; medium effort; run counts, scoring variants, and dates are recorded per result.
未知项
Healthcare evaluations use benchmark-specific run counts and scoring variants.
工具
禁止工具
推理预算
medium
框架
未记录
协议
HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
条件
medium effort; one run per level below max and five runs at max. Runs below max were made October 5; max is a five-run mean from October 2. Labeled figure value.

直接支持该成绩

在排名中查看此成绩
Length-adjusted score60.3%原文 60.3% · 单位 %
公布 未确认
Healthcare evaluations / high
设置
Safety classifiers enabled; high effort; run counts, scoring variants, and dates are recorded per result.
未知项
Healthcare evaluations use benchmark-specific run counts and scoring variants.
工具
禁止工具
推理预算
high
框架
未记录
协议
HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
条件
high effort; one run per level below max and five runs at max. Runs below max were made October 5; max is a five-run mean from October 2. Labeled figure value.

直接支持该成绩

在排名中查看此成绩
Length-adjusted score61.1%原文 61.1% · 单位 %
公布 未确认
Healthcare evaluations / xhigh
设置
Safety classifiers enabled; xhigh effort; run counts, scoring variants, and dates are recorded per result.
未知项
Healthcare evaluations use benchmark-specific run counts and scoring variants.
工具
禁止工具
推理预算
xhigh
框架
未记录
协议
HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
条件
xhigh effort; one run per level below max and five runs at max. Runs below max were made October 5; max is a five-run mean from October 2. Labeled figure value.

直接支持该成绩

在排名中查看此成绩
Length-adjusted score61.6%原文 61.6% · 单位 %
公布 未确认
Healthcare evaluations / max
设置
Safety classifiers enabled; max effort; run counts, scoring variants, and dates are recorded per result.
未知项
Healthcare evaluations use benchmark-specific run counts and scoring variants.
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
条件
max effort; one run per level below max and five runs at max. Runs below max were made October 5; max is a five-run mean from October 2. Labeled figure value.

直接支持该成绩

在排名中查看此成绩